Abstract: Automatic License plate recognition (ALPR) is a technology which recognizes the registration plate or number plate or License plate of a vehicle. In this paper, an Indian vehicle number plate is mined and the characters are predicted in efficient manner. ALPR involves four major technique i) Pre-processing ii) License Plate Location Identification iii) Individual Character Segmentation iv) Character Recognition. The opening phase, named pre-processing helps to remove noises and enhances the quality of the image using the conception of Morphological Operation and Image subtraction. The second phase, the most puzzling stage ascertain the location of license plate using the protocol Canny Edge detection, dilation and erosion. In the third phase, each characters characterized by Connected Component Approach (CCA) and in the ending phase, each segmented characters are conceptualized using cross correlation template matching- a scheme specifically appropriate for fixed format. Major application of ALPR is Tolling collection, Border Control, Parking, Stolen cars, Enforcement, Access Control, Traffic control. The database consists of 500 car images taken under dissimilar lighting condition is used. The efficiency of the system is 97%. Our future focus is Indian Vehicle License Plate Validation (Whether License plate of a vehicle is as per Road transport and highway standard).
Abstract: Speaker Identification (SI) is the task of establishing
identity of an individual based on his/her voice characteristics. The SI
task is typically achieved by two-stage signal processing: training and
testing. The training process calculates speaker specific feature
parameters from the speech and generates speaker models
accordingly. In the testing phase, speech samples from unknown
speakers are compared with the models and classified. Even though
performance of speaker identification systems has improved due to
recent advances in speech processing techniques, there is still need of
improvement. In this paper, a Closed-Set Tex-Independent Speaker
Identification System (CISI) based on a Multiple Classifier System
(MCS) is proposed, using Mel Frequency Cepstrum Coefficient
(MFCC) as feature extraction and suitable combination of vector
quantization (VQ) and Gaussian Mixture Model (GMM) together
with Expectation Maximization algorithm (EM) for speaker
modeling. The use of Voice Activity Detector (VAD) with a hybrid
approach based on Short Time Energy (STE) and Statistical
Modeling of Background Noise in the pre-processing step of the
feature extraction yields a better and more robust automatic speaker
identification system. Also investigation of Linde-Buzo-Gray (LBG)
clustering algorithm for initialization of GMM, for estimating the
underlying parameters, in the EM step improved the convergence rate
and systems performance. It also uses relative index as confidence
measures in case of contradiction in identification process by GMM
and VQ as well. Simulation results carried out on voxforge.org
speech database using MATLAB highlight the efficacy of the
proposed method compared to earlier work.
Abstract: The purpose of this study is the discrimination of 28
postmenopausal with osteoporotic femoral fractures from an agematched
control group of 28 women using texture analysis based on
fractals. Two pre-processing approaches are applied on radiographic
images; these techniques are compared to highlight the choice of the
pre-processing method. Furthermore, the values of the fractal
dimension are compared to those of the fractal signature in terms of
the classification of the two populations. In a second analysis, the
BMD measure at proximal femur was compared to the fractal
analysis, the latter, which is a non-invasive technique, allowed a
better discrimination; the results confirm that the fractal analysis of
texture on calcaneus radiographs is able to discriminate osteoporotic
patients with femoral fracture from controls. This discrimination was
efficient compared to that obtained by BMD alone. It was also
present in comparing subgroups with overlapping values of BMD.
Abstract: In this paper, we propose moving object detection
method which is helpful for driver to safely take his/her car out of
parking lot. When moving objects such as motorbikes, pedestrians,
the other cars and some obstacles are detected at the rear-side of host
vehicle, the proposed algorithm can provide to driver warning. We
assume that the host vehicle is just before departure. Gaussian
Mixture Model (GMM) based background subtraction is basically
applied. Pre-processing such as smoothing and post-processing as
morphological filtering are added. We examine “which color space
has better performance for detection of moving objects?” Three color
spaces including RGB, YCbCr, and Y are applied and compared, in
terms of detection rate. Through simulation, we prove that RGB
space is more suitable for moving object detection based on
background subtraction.
Abstract: In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation,
style, illumination, and can suffer from perspective distortion.
Pre-processing is performed to make the characters scale and
rotation invariant. Since text degradations can not be appropriately
defined using well-known geometric transformations such
as translation, rotation, affine transformation and shearing, we
use the whole character black pixels as our feature vector.
Classification is performed with minimum distance classifier
using the maximum likelihood criterion, which delivers very
promising Character Recognition Rate (CRR) of 89%. We
achieve considerably higher Word Recognition Rate (WRR) of
99% when using lower level linguistic knowledge about product
words during the recognition process.
Abstract: Real time image and video processing is a demand in
many computer vision applications, e.g. video surveillance, traffic
management and medical imaging. The processing of those video
applications requires high computational power. Thus, the optimal
solution is the collaboration of CPU and hardware accelerators. In
this paper, a Canny edge detection hardware accelerator is proposed.
Edge detection is one of the basic building blocks of video and image
processing applications. It is a common block in the pre-processing
phase of image and video processing pipeline. Our presented
approach targets offloading the Canny edge detection algorithm from
processing system (PS) to programmable logic (PL) taking the
advantage of High Level Synthesis (HLS) tool flow to accelerate the
implementation on Zynq platform. The resulting implementation
enables up to a 100x performance improvement through hardware
acceleration. The CPU utilization drops down and the frame rate
jumps to 60 fps of 1080p full HD input video stream.
Abstract: Floods play a key role in landform evolution of an
area. This process is likely to alter the topography of the earth’s
surface. The present study area, Kota Bharu is very prone to floods
extends from upstream of Kelantan River near Kemubu to the
downstream area near Kuala Besar. These flood events which occur
every year in the study area exhibit a strong bearing on river
morphological set-up. In the present study, three satellite imageries of
different time periods have been used to manifest the post-flood
landform changes. The pre-processing of the images such as subset,
geometric corrections and atmospheric corrections were carried-out
using ENVI 4.5 followed by the analysis processes. Twenty sets of
cross sections were plotted using software Erdas 9.2, ERDAS and
ArcGis 10 for the all three images. The results show a significant
change in the length of the cross section which suggest that the
geomorphological processes play a key role in carving and shaping
the river banks during the floods.
Abstract: In this research work, neural networks were applied to
classify two types of hip joint implants based on the relative hip joint
implant side speed and three components of each ground reaction
force. The condition of walking gait at normal velocity was used and
carried out with each of the two hip joint implants assessed. Ground
reaction forces’ kinetic temporal changes were considered in the first
approach followed but discarded in the second one. Ground reaction
force components were obtained from eighteen patients under such
gait condition, half of which had a hip implant type I-II, whilst the
other half had the hip implant, defined as type III by Orthoload®.
After pre-processing raw gait kinetic data and selecting the time
frames needed for the analysis, the ground reaction force components
were used to train a MLP neural network, which learnt to distinguish
the two hip joint implants in the abovementioned condition. Further
to training, unknown hip implant side and ground reaction force
components were presented to the neural networks, which assigned
those features into the right class with a reasonably high accuracy for
the hip implant type I-II and the type III. The results suggest that
neural networks could be successfully applied in the performance
assessment of hip joint implants.
Abstract: In this paper, the comparison between k-Nearest Neighbor (kNN) algorithms for classifying the 3D EEG model in brain balancing is presented. The EEG signal recording was conducted on 51 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, maximum PSD values were extracted as features from the model. There are three indexes for balanced brain; index 3, index 4 and index 5. There are significant different of the EEG signals due to the brain balancing index (BBI). Alpha-α (8–13 Hz) and beta-β (13–30 Hz) were used as input signals for the classification model. The k-NN classification result is 88.46% accuracy. These results proved that k-NN can be used in order to predict the brain balancing application.
Abstract: This paper discusses on power spectral density (PSD) characteristics which are extracted from three-dimensional (3D) electroencephalogram (EEG) models. The EEG signal recording was conducted on 150 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, the values of maximum PSD were extracted as features from the model. These features are analyzed using mean relative power (MRP) and different mean relative power (DMRP) technique to observe the pattern among different brain balancing indexes. The results showed that by implementing these techniques, the pattern of brain balancing indexes can be clearly observed. Some patterns are indicates between index 1 to index 5 for left frontal (LF) and right frontal (RF).
Abstract: The proposed method is to study and analyze Electrocardiograph (ECG) waveform to detect abnormalities present with reference to P, Q, R and S peaks. The first phase includes the acquisition of real time ECG data. In the next phase, generation of signals followed by pre-processing. Thirdly, the procured ECG signal is subjected to feature extraction. The extracted features detect abnormal peaks present in the waveform Thus the normal and abnormal ECG signal could be differentiated based on the features extracted. The work is implemented in the most familiar multipurpose tool, MATLAB. This software efficiently uses algorithms and techniques for detection of any abnormalities present in the ECG signal. Proper utilization of MATLAB functions (both built-in and user defined) can lead us to work with ECG signals for processing and analysis in real time applications. The simulation would help in improving the accuracy and the hardware could be built conveniently.
Abstract: Various fairness models and criteria proposed by academia and industries for wired networks can be applied for ad hoc wireless network. The end-to-end fairness in an ad hoc wireless network is a challenging task compared to wired networks, which has not been addressed effectively. Most of the traffic in an ad hoc network are transport layer flows and thus the fairness of transport layer flows has attracted the interest of the researchers. The factors such as MAC protocol, routing protocol, the length of a route, buffer size, active queue management algorithm and the congestion control algorithms affects the fairness of transport layer flows. In this paper, we have considered the rate of data transmission, the queue management and packet scheduling technique. The ad hoc network is dynamic in nature due to various parameters such as transmission of control packets, multihop nature of forwarding packets, changes in source and destination nodes, changes in the routing path influences determining throughput and fairness among the concurrent flows. In addition, the effect of interaction between the protocol in the data link and transport layers has also plays a role in determining the rate of the data transmission. We maintain queue for each flow and the delay information of each flow is maintained accordingly. The pre-processing of flow is done up to the network layer only. The source and destination address information is used for separating the flow and the transport layer information is not used. This minimizes the delay in the network. Each flow is attached to a timer and is updated dynamically. Finite State Machine (FSM) is proposed for queue and transmission control mechanism. The performance of the proposed approach is evaluated in ns-2 simulation environment. The throughput and fairness based on mobility for different flows used as performance metrics. We have compared the performance of the proposed approach with ATP and the transport layer information is used. This minimizes the delay in the network. Each flow is attached to a timer and is updated dynamically. Finite State Machine (FSM) is proposed for queue and transmission control mechanism. The performance of the proposed approach is evaluated in ns-2 simulation environment. The throughput and fairness based on not mobility for different flows used as performance metrics. We have compared the performance of the proposed approach with ATP and MC-MLAS and the performance of the proposed approach is encouraging.
Abstract: Pasta is one of the most widely consumed food products around the world. Rapid determination of the moisture content in pasta will assist food processors to provide online quality control of pasta during large scale production. Rapid Fourier transform near-infrared method (FT-NIR) was developed for determining moisture content in pasta. A calibration set of 150 samples, a validation set of 30 samples and a prediction set of 25 samples of pasta were used. The diffuse reflection spectra of different types of pastas were measured by FT-NIR analyzer in the 4,000-12,000cm-1 spectral range. Calibration and validation sets were designed for the conception and evaluation of the method adequacy in the range of moisture content 10 to 15 percent (w.b) of the pasta. The prediction models based on partial least squares (PLS) regression, were developed in the near-infrared. Conventional criteria such as the R2, the root mean square errors of cross validation (RMSECV), root mean square errors of estimation (RMSEE) as well as the number of PLS factors were considered for the selection of three pre-processing (vector normalization, minimum-maximum normalization and multiplicative scatter correction) methods. Spectra of pasta sample were treated with different mathematic pre-treatments before being used to build models between the spectral information and moisture content. The moisture content in pasta predicted by FT-NIR methods had very good correlation with their values determined via traditional methods (R2 = 0.983), which clearly indicated that FT-NIR methods could be used as an effective tool for rapid determination of moisture content in pasta. The best calibration model was developed with min-max normalization (MMN) spectral pre-processing (R2 = 0.9775). The MMN pre-processing method was found most suitable and the maximum coefficient of determination (R2) value of 0.9875 was obtained for the calibration model developed.
Abstract: In this study, we analyzed the factors that affect research funds using linear regression analysis to increase the effectiveness of investments in national research projects. We collected 7,916 items of data on research projects that were in the process of being finished or were completed between 2010 and 2011. Data pre-processing and visualization were performed to derive statistically significant results. We identified factors that affected funding using analysis of fit distributions and estimated increasing or decreasing tendencies based on these factors.
Abstract: Red blood cells (RBCs) are among the most
commonly and intensively studied type of blood cells in cell biology.
Anemia is a lack of RBCs is characterized by its level compared to
the normal hemoglobin level. In this study, a system based image
processing methodology was developed to localize and extract RBCs
from microscopic images. Also, the machine learning approach is
adopted to classify the localized anemic RBCs images. Several
textural and geometrical features are calculated for each extracted
RBCs. The training set of features was analyzed using principal
component analysis (PCA). With the proposed method, RBCs were
isolated in 4.3secondsfrom an image containing 18 to 27 cells. The
reasons behind using PCA are its low computation complexity and
suitability to find the most discriminating features which can lead to
accurate classification decisions. Our classifier algorithm yielded
accuracy rates of 100%, 99.99%, and 96.50% for K-nearest neighbor
(K-NN) algorithm, support vector machine (SVM), and neural
network RBFNN, respectively. Classification was evaluated in highly
sensitivity, specificity, and kappa statistical parameters. In
conclusion, the classification results were obtained within short time
period, and the results became better when PCA was used.
Abstract: The image segmentation method described in this
paper has been developed as a pre-processing stage to be used in
methodologies and tools for video/image indexing and retrieval by
content. This method solves the problem of whole objects extraction
from background and it produces images of single complete objects
from videos or photos. The extracted images are used for calculating
the object visual features necessary for both indexing and retrieval
processes.
The segmentation algorithm is based on the cooperation among an
optical flow evaluation method, edge detection and region growing
procedures. The optical flow estimator belongs to the class of
differential methods. It permits to detect motions ranging from a
fraction of a pixel to a few pixels per frame, achieving good results in
presence of noise without the need of a filtering pre-processing stage
and includes a specialised model for moving object detection.
The first task of the presented method exploits the cues from
motion analysis for moving areas detection. Objects and background
are then refined using respectively edge detection and seeded region
growing procedures. All the tasks are iteratively performed until
objects and background are completely resolved.
The method has been applied to a variety of indoor and outdoor
scenes where objects of different type and shape are represented on
variously textured background.
Abstract: In this paper, an automatic detecting algorithm for
QRS complex detecting was applied for analyzing ECG recordings
and five criteria for dangerous arrhythmia diagnosing are applied for a
protocol type of automatic arrhythmia diagnosing system. The
automatic detecting algorithm applied in this paper detected the
distribution of QRS complexes in ECG recordings and related
information, such as heart rate and RR interval. In this investigation,
twenty sampled ECG recordings of patients with different pathologic
conditions were collected for off-line analysis. A combinative
application of four digital filters for bettering ECG signals and
promoting detecting rate for QRS complex was proposed as
pre-processing. Both of hardware filters and digital filters were
applied to eliminate different types of noises mixed with ECG
recordings. Then, an automatic detecting algorithm of QRS complex
was applied for verifying the distribution of QRS complex. Finally,
the quantitative clinic criteria for diagnosing arrhythmia were
programmed in a practical application for automatic arrhythmia
diagnosing as a post-processor. The results of diagnoses by automatic
dangerous arrhythmia diagnosing were compared with the results of
off-line diagnoses by experienced clinic physicians. The results of
comparison showed the application of automatic dangerous
arrhythmia diagnosis performed a matching rate of 95% compared
with an experienced physician-s diagnoses.
Abstract: This paper presents a wavelet transform and Support
Vector Machine (SVM) based algorithm for estimating fault location
on transmission lines. The Discrete wavelet transform (DWT) is used
for data pre-processing and this data are used for training and testing
SVM. Five types of mother wavelet are used for signal processing to
identify a suitable wavelet family that is more appropriate for use in
estimating fault location. The results demonstrated the ability of SVM
to generalize the situation from the provided patterns and to
accurately estimate the location of faults with varying fault resistance.
Abstract: In the end of the day, meteorological data and environmental data becomes widely used such as plant varieties selection system. Variety plant selection for planted area is of almost importance for all crops, including varieties of sugarcane. Since sugarcane have many varieties. Variety plant non selection for planting may not be adapted to the climate or soil conditions for planted area. Poor growth, bloom drop, poor fruit, and low price are to be from varieties which were not recommended for those planted area. This paper presents plant varieties selection system for planted areas in Thailand from meteorological data and environmental data by the use of decision tree techniques. With this software developed as an environmental data analysis tool, it can analyze resulting easier and faster. Our software is a front end of WEKA that provides fundamental data mining functions such as classify, clustering, and analysis functions. It also supports pre-processing, analysis, and decision tree output with exporting result. After that, our software can export and display data result to Google maps API in order to display result and plot plant icons effectively.
Abstract: Many factors affect the success of Machine Learning
(ML) on a given task. The representation and quality of the instance
data is first and foremost. If there is much irrelevant and redundant
information present or noisy and unreliable data, then knowledge
discovery during the training phase is more difficult. It is well known
that data preparation and filtering steps take considerable amount of
processing time in ML problems. Data pre-processing includes data
cleaning, normalization, transformation, feature extraction and
selection, etc. The product of data pre-processing is the final training
set. It would be nice if a single sequence of data pre-processing
algorithms had the best performance for each data set but this is not
happened. Thus, we present the most well know algorithms for each
step of data pre-processing so that one achieves the best performance
for their data set.